arXiv (Cornell University) · 2023 · 10 citations · 0 references
ComputingComputer ScienceComputer VisionMachine LearningNatural Language ProcessingAction RecognitionMulti-task LearningSequence LearningVideo AnalysisAction DetectionActivity RecognitionDirected Acyclic Task GraphsTask Graph AnalysisTask Graph ModelsTask GraphsVideo Representation LearningZero-shot Action Recognition
Procedural activity understanding requires perceiving human actions in terms of a broader task, where multiple keysteps are performed in sequence across a long video to reach a final goal state -- such as the steps of a recipe or a DIY fix-it task. Prior work largely treats keystep recognition in isolation of this broader structure, or else rigidly confines keysteps to align with a predefined sequential script. We propose discovering a task graph automatically from how-to videos to represent probabilistically how people tend to execute keysteps, and then leverage this graph to regularize keystep recognition in novel videos. On multiple datasets of real-world instructional videos, we show the impact: more reliable zero-shot keystep localization and improved video representation learning, exceeding the state of the art.